DiscoLM-120b-AWQ / config.json
TheBloke's picture
AWQ model commit
fa55c66
raw
history blame contribute delete
848 Bytes
{
"_name_or_path": "/workspace/process/discoresearch_discolm-120b/source",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 28672,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 64,
"num_hidden_layers": 137,
"num_key_value_heads": 8,
"pad_token_id": 0,
"pretraining_tp": 1,
"quantization_config": {
"bits": 4,
"group_size": 128,
"quant_method": "awq",
"version": "gemm",
"zero_point": true
},
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.35.2",
"use_cache": true,
"vocab_size": 32032
}